sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [PD][Spec] Give a PD decode's first EAGLE draft step a proposal distribution
- Fix tokenize responses to report the server context limit
- [DSA] Q8KV8 FP8 Sparse Prefill on GLM-5.3-Flash with BF16 KV Cache
- [Plugin] Foundry CUDA-graph persistence: FOUNDRY_GRAPH_EXTENSION_CONFIG, fail-fast loader, contract and e2e tests
- [MM] Derive Kimi image cache identity from full content digest and preprocessing config
- [AMD] Keep the FP4 varctx schedule test off AITER's 2048-row compile
- [AMD][Quark] Lay out Quark weights to speed up ROCm decoding
- [Fix] Preserve launcher identity for worker failure signals
- fix(tokenizer): tolerate custom _pad() overrides missing padding_side
- fix(transformers-backend): support legacy tied-weights + wrapped-model remote code
- Docs
- Python not yet supported